From 32f9c5fe68800376e730ad1cecd5ea4537d573c8 Mon Sep 17 00:00:00 2001
From: Pablo Hoffman <pablo@pablohoffman.com>
Date: Thu, 1 Apr 2010 04:05:53 -0300
Subject: [PATCH] removed old untested (and probably broken) code

---
 extras/sql/scraping.sql         | 72 ---------------------------------
 scrapy/stats/collector/mysql.py | 31 --------------
 2 files changed, 103 deletions(-)
 delete mode 100644 extras/sql/scraping.sql
 delete mode 100644 scrapy/stats/collector/mysql.py

diff --git a/extras/sql/scraping.sql b/extras/sql/scraping.sql
deleted file mode 100644
index c3314f5a1..000000000
--- a/extras/sql/scraping.sql
+++ /dev/null
@@ -1,72 +0,0 @@
-DROP TABLE IF EXISTS `url_history`;
-DROP TABLE IF EXISTS `version`;
-DROP TABLE IF EXISTS `url_status`;
-DROP TABLE IF EXISTS `ticket`;
-DROP TABLE IF EXISTS `domain_stats`;
-DROP TABLE IF EXISTS `domain_stats_history`;
-DROP TABLE IF EXISTS `domain_data_history`;
-
-CREATE TABLE `ticket` (
-  `guid` char(40) NOT NULL,
-  `domain` varchar(255) default NULL,
-  `url` varchar(2048) default NULL,
-  `url_hash` char(40) default NULL, -- so we can join to url_status
-  PRIMARY KEY  (`guid`)
-) ENGINE=InnoDB DEFAULT CHARSET=utf8;
-
-CREATE TABLE `version` (
-  `id` bigint(20) NOT NULL auto_increment,
-  `guid` char(40) NOT NULL,
-  `version` char(40) NOT NULL,
-  `seen` datetime NOT NULL,
-  PRIMARY KEY  (`id`),
-  FOREIGN KEY (`guid`) REFERENCES ticket(guid) ON UPDATE CASCADE ON DELETE CASCADE,
-  UNIQUE KEY (`version`)
-) ENGINE=InnoDB DEFAULT CHARSET=utf8;
-
-CREATE TABLE `url_status` (
-  -- see http://support.microsoft.com/kb/q208427/ for explanation of 2048
-  `url_hash` char(40) NOT NULL,         -- for faster searches
-  `url` varchar(2048) NOT NULL,
-  `parent_hash` char(40) default NULL,  -- the url that was followed to this one - for reporting
-  `last_version` char(40) default NULL, -- can be null if it generated an error the last time is was checked
-  `last_checked`  datetime NOT NULL,
-  PRIMARY KEY  (`url_hash`)
-) ENGINE=InnoDB DEFAULT CHARSET=utf8;
-
-CREATE TABLE `url_history` (
-   `url_hash` char(40) NOT NULL,
-   `version` char(40) NOT NULL,
-   `postdata_hash` char(40) default NULL,
-   `created` datetime NOT NULL,
-   PRIMARY KEY (`version`),
-   FOREIGN KEY (`url_hash`) REFERENCES url_status(url_hash) ON UPDATE CASCADE ON DELETE CASCADE
-) ENGINE=InnoDB DEFAULT CHARSET=utf8;
-
-CREATE TABLE `domain_stats` (
-  `key1` varchar(128) NOT NULL,
-  `key2` varchar(128) NOT NULL,
-  `value` text,
-  PRIMARY KEY `key1_key2` (`key1`, `key2`),
-  KEY `key1` (`key1`)
-) ENGINE=InnoDB DEFAULT CHARSET=utf8;
-
-CREATE TABLE `domain_stats_history` (
-  `id` bigint(20) NOT NULL auto_increment,
-  `key1` varchar(128) NOT NULL,
-  `key2` varchar(128) NOT NULL,
-  `value` varchar(2048) NOT NULL,
-  `stored` datetime NOT NULL,
-  PRIMARY KEY  (`id`),
-  KEY `key1_key2` (`key1`, `key2`),
-  KEY `key1` (`key1`),
-  KEY `stored` (`stored`)
-) ENGINE=InnoDB DEFAULT CHARSET=utf8;
-
-CREATE TABLE `domain_data_history` (
-  `domain` varchar(255) NOT NULL,
-  `stored` datetime NOT NULL,
-  `data` text,
-  KEY `domain_stored` (`domain`, `stored`),
-  KEY `domain` (`domain`)
-) ENGINE=InnoDB DEFAULT CHARSET=utf8;
diff --git a/scrapy/stats/collector/mysql.py b/scrapy/stats/collector/mysql.py
deleted file mode 100644
index 2cf145347..000000000
--- a/scrapy/stats/collector/mysql.py
+++ /dev/null
@@ -1,31 +0,0 @@
-"""
-A Stats collector for persisting stats (pickled) to a MySQL db
-"""
-
-import cPickle as pickle
-from datetime import datetime
-
-from scrapy.stats.collector import StatsCollector
-from scrapy.utils.mysql import mysql_connect
-from scrapy.conf import settings
-
-class MysqlStatsCollector(StatsCollector):
-
-    def __init__(self):
-        super(MysqlStatsCollector, self).__init__()
-        mysqluri = settings['STATS_MYSQL_URI']
-        self._mysql_conn = mysql_connect(mysqluri, use_unicode=False) if mysqluri else None
-        
-    def _persist_stats(self, stats, spider=None):
-        if spider is None: # only store spider-specific stats
-            return
-        if self._mysql_conn is None:
-            return
-        stored = datetime.utcnow()
-        datas = pickle.dumps(stats)
-        table = 'domain_data_history'
-
-        c = self._mysql_conn.cursor()
-        c.execute("INSERT INTO %s (domain,stored,data) VALUES (%%s,%%s,%%s)" % table, \
-            (spider.domain_name, stored, datas))
-        self._mysql_conn.commit()